Standard inductive learning requires that training and test instances come from the same distribution. Transfer learning seeks to remove this restriction. In shallow transfer, tes...
Abstract. This paper is about the evaluation of the results of clustering algorithms, and the comparison of such algorithms. We propose a new method based on the enrichment of a se...
A new class of nonparametric algorithms for high-dimensional binary classification is proposed using cascades of low dimensional polynomial structures. Construction of polynomial ...
Sander M. Bohte, Markus Breitenbach, Gregory Z. Gr...
Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtai...
Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, ...
Deep learning has been successfully applied to perform non-linear embedding. In this paper, we present supervised embedding techniques that use a deep network to collapse classes....
Martin Renqiang Min, Laurens van der Maaten, Zinen...